1. Interpreting evidence 2

Question 1

Confidence interval, what is it?

Answer 1

A confidence interval gives a range of values, estimated from the sample data, which is likely to include the, unknown, population parameter (e.g. mean , RR, OR)

i.e. describes the uncertainty of the estimate

Question 2

What is a 95% CI?

Answer 2

A 95% confidence interval is a range of values within which we are 95% confident the true population mean lies (roughly speaking)

Question 3

Wider the confidence interval, _____ certain we are about the estimate

Answer 3

Wider the confidence interval, less certain we are about the estimate

Question 4

OR?

Answer 4

Odd ratio

-Size of the effect of intervention compared to control

Question 5

What is Ho?

Answer 5

Null hypothesis

Question 6

What is H1?

Answer 6

Alternative/research hypothesis

Question 7

How does Confidence intervals indicate significance?

Answer 7

If two CI’s around two means don’t overlap then it shows the difference in results is highly significant

Question 8

Purpose of T test?

Answer 8

Allows us to statistically COMPARE MEANS between two groups
T-test is used to determine whether two means are significantly different from each other

Gives: A probability (p-value) that such a difference (or a greater difference) would be found by chance, IF THE NULL HYPOTHESIS IS TRUE

Question 9

Purpose chi-square test?

Answer 9

Allows us to statistically COMPARE FREQUENCIES
Allows us to statistically determine if the difference between the observed and expected numbers in each cell is significant (GIVEN THE SAMPLE SIZE)

Question 10

Degree of freedom? “df”

Answer 10

Sample number - 1

Question 11

Cut-off for P-value?

Answer 11

p<0.05

Here the Null hypothesis can be rejected. So alternative/research hypothesis is accepted (there is a difference).

–> “There is a significant difference”

Question 12

What are the 3 different t-tests?

Answer 12

– Comparison of mean with a single value (e.g. mean BP in sample vs
literature standard value)
– Comparison of means of independent samples (mean effect of statin 1 vs statin 2)
– Comparison of means of paired data ( BP before and after treatment measured in the same people)

Question 13

If a difference between observed and expected results is found, then implies…

Answer 13

a “relationship” or “association”

– i.e values of one variable may influence values of the other

Question 14

What is the difference between chi-square test for independence and goodness to fit?

Answer 14

Chi-square test for independence…
• association between two categorical variables (e.g: Is cholesterol status associated with gender?)

Chi-square test for goodness to fit…
Tests the difference between frequencies of a single categorical variable and some hypothesised frequency

Question 15

What is meant by correlation?

Answer 15

Measures the strength of relationship between two numerical variables

Question 16

How is correlation measured?

Answer 16

Correlation coefficient (r)

Varies between -1 and +1
Where r= -1 means a perfect negative correlation
Where r= +1 means a perfect positive correlation

Question 17

What is a strong positive correlation?

Answer 17

r= +0.6 –> + 1

Question 18

What is the use of linear regression?

Answer 18

Used to predict relationship between independent variables and an outcome/ dependent variable

• Must be a linear relationship between independent and outcome
• Is an example of a model. Want to predict the change in outcome associated with a particular change in the independent variable
• Models estimate the regression coefficient which can be thought of as the slope of the best –fitting straight line through a scatter plot of the data
• Closely related to correlation

Question 19

Equation for linear regression?

Answer 19

• Y=bX + c (intercept)

* b/B/”beta”= slope of best fitting straight line. “Regression coefficient”

Question 20

Confidence intervals and regression coefficient (b/B/”beta”)

Answer 20

The regression coefficient (b) has a confidence interval.

P-value for this coefficient indicates probability that the ‘true’ slope of the line is = 0 (i.e Null hypothesis is NO SLOPE).

Significant p-value (p<0.05) indicates that there is a significant slope (i.e b not equal to 0)

Question 21

What variables are used in t-test?

Answer 21

– 1 dependent continuous variable (e.g height)

– 1 independent BINARY categorical variable (e.g. sex)

Question 22

What variables are used in chi-square test?

Answer 22

– 1 dependent categorical variable (e.g. alternative drug types)
– 1 independent categorical variable (e.g. Deprivation category)